Downloads · 30 days
0
proj-airi/games-balatro-2024-yolo-card-identity-detection-mod-ground-truth
games-balatro-2024-yolo-card-identity-detection-mod-ground-truth is a machine learning model from proj-airi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
<p align="center"<img src="./docs/cover.png"</p
Downloads · 30 days
0
Access
Public
Updated Aug 4, 2026
Repo size
23.6 MB
Likes
0
Public
Click a slice to open those files.
.onnx10.9 MB · 46%
From the Hugging Face model README
YOLO11n detector for 54 exact card identities, card backs, and unreadable rank/suit. This model is part of the Project AIRI game-playing work.
model.pt: Ultralytics/PyTorch checkpoint.onnx/model.onnx: fixed-shape ONNX export at 960 px.docs/: training curves, confusion matrices, and prediction examples.| Metric | Value |
|---|---|
| Precision | 0.956027 |
| Recall | 0.945068 |
| mAP50 | 0.977525 |
The train/validation/test split is grouped by generated game round. Metrics describe the Mod-generated distribution and are not a claim of identical accuracy on arbitrary live captures.
| Batch 0 | Batch 1 | Batch 2 |
|---|---|---|
![]() | ![]() | ![]() |


MIT.